Papers with Code 아카이브

Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

39

평가표

124

보존된 평가 기록

977

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Artsplendr/Medical-Images-Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/ArturoDeza/Piranhas

Object Detection Through Exploration With A Foveated Visual Field

https://github.com/AryaKoureshi/Brain-tumor-detection

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/Aryavir07/Detecting-Brain-Tumor-Using-Deep-Learning

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/AsahiLiu/PointDetectron

Deep Hough Voting for 3D Object Detection in Point Clouds

https://github.com/Ashish-Sankritya/darknet_CNN

YOLOv4: Optimal Speed and Accuracy of Object Detection

https://github.com/AshishSingh2261/Pedestrian_Instance_Segmentation

Mask R-CNN

https://github.com/Asteur/relation-network

Relation Networks for Object Detection

https://github.com/Asthestarsfalll/BiSeNet-MegEngine

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

https://github.com/Asthestarsfalll/ConvNeXt-MegEngine

A ConvNet for the 2020s

https://github.com/Asthestarsfalll/IBNNet-MegEngine

Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net

https://github.com/Asthestarsfalll/MAE-MegEngine

Masked Autoencoders Are Scalable Vision Learners

https://github.com/Asthestarsfalll/PSPNet-MegEngine

Pyramid Scene Parsing Network

https://github.com/Asthestarsfalll/ResNeSt-MegEngine

ResNeSt: Split-Attention Networks

https://github.com/Asthestarsfalll/SENet-MegEngine

Squeeze-and-Excitation Networks

https://github.com/Asthestarsfalll/UniFormer-MegEngine

UniFormer: Unifying Convolution and Self-attention for Visual Recognition

https://github.com/Asthestarsfalll/VAN-MegEngine

Visual Attention Network

https://github.com/AtlasCoCo/Darknet

YOLO9000: Better, Faster, Stronger

https://github.com/Atom-min/MLBigWork

YOLOv3: An Incremental Improvement

https://github.com/AutoVision-cloud/DeformablePVRCNN

Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations

https://github.com/AutomatedAI/deeplab_inference

Rethinking Atrous Convolution for Semantic Image Segmentation

https://github.com/AutomatedAI/deeplab_segmentation_example

Rethinking Atrous Convolution for Semantic Image Segmentation

https://github.com/Autonomous-Visual-Perception/detection-benchmark

MMDetection: Open MMLab Detection Toolbox and Benchmark

https://github.com/AviTewari/Lake-Ice-Monitoring

U-Net: Convolutional Networks for Biomedical Image Segmentation

https://github.com/Awia00/Predicted-Path-Tracing

Feature Pyramid Networks for Object Detection

https://github.com/AyushAniket/ResNET-and-various-normalizations

Deep Residual Learning for Image Recognition

https://github.com/BBuf/Darknet

YOLO9000: Better, Faster, Stronger

https://github.com/BIG-CHENG/FaceRec

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

https://github.com/BIGBALLON/distribuuuu

Bottleneck Transformers for Visual Recognition

https://github.com/BIYTC/mobilenet_maskrcnn

RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free

https://github.com/BMIRDS/deepslide

Attention-Based Deep Neural Networks for Detection of Cancerous and Precancerous Esophagus Tissue on Histopathological Slides

https://github.com/BOBrown/deeparsing-master

Pyramid Scene Parsing Network

https://github.com/BPMJG/annotated-F-pointnet

Frustum PointNets for 3D Object Detection from RGB-D Data

https://github.com/BPMJG/annotated_pointnet

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/PVTv2

PVT v2: Improved Baselines with Pyramid Vision Transformer

https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/Shuffle_Transformer

Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.